bf16 Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Nemotron-3-Ultra-550B-A55B-bf16 --prompt "Hello"
Details
- Base model
- nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 (finetune) · NVIDIA Nemotron 3 Ultra 550B A55B BF16 on the radar →
- Vendor
- NVIDIA
- Task
- Text generation
- Quantisation
- bf16
- Licence
- nvidia-open-model-license
- Downloads
- 0 in the last 30 days · 0 all time · 0 likes
- Published
- 2026-06-04 · updated 2026-06-04 (5mo ago)
- Tags
- nemotron
Other MLX builds of nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Nemotron-3-Ultra-550B-A55B-4bit | 4-bit | ≈ 313 GB | 512 GB+ | 341 |
| Nemotron-3-Ultra-550B-A55B-bf16 (this one) | bf16 | — | — | 0 |